F2G-Pose is a real‑time, single‑pass framework for category‑level RGB‑D object pose estimation that predicts 3D rotation, translation, metric size, and a completed camera‑frame shape from a single RGB‑D observation. It lifts dense visual foundation features to partial point clouds, encodes local geometry with DGCNN tokenization, and uses a Mixture‑of‑Experts Transformer to integrate object‑level structure. Trained only on pose‑annotated synthetic SOPE data and leveraging a frozen RADIO backbone, F2G‑Pose achieves state‑of‑the‑art accuracy on SOPE and ROPE while running at 28 FPS for pose‑only inference and demonstrates strong geometry completion on HouseCat6D and real‑object transfer on HANDAL.
By Jinyu Zhang, Haitao Lin, Jiashu Hou, Xiangyang Xue, Yanwei Fu
F2G-Pose is a real‑time, single‑pass framework for category‑level RGB‑D object pose estimation that predicts pose, metric size, and camera‑frame completed shape from a single RGB‑D observation. It lifts dense visual foundation features to partial point clouds, encodes local geometry with DGCNN tokenization, and uses a Mixture‑of‑Experts Transformer to integrate object‑level structure. Trained only on pose‑annotated synthetic SOPE data with a frozen RADIO backbone, it achieves state‑of‑the‑art accuracy on SOPE and ROPE while running at 28 FPS for pose‑only inference and demonstrates strong geometry on HouseCat6D and real‑object transfer on HANDAL.
Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving efficient use of rig geometry a challenge. We present...
arXiv:2609.40244v1 Announce Type: new
Abstract: Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving effi...
By Yufei Wei, Shuhao Ye, Qi Wang, Xin Zheng, Qing Huang, Rong Xiong, Yue Wang
The paper introduces CalfVO, a monocular visual odometry system that operates without camera intrinsics, test‑time optimization, bundle adjustment, or loop closure. Using a transformer, it predicts relative poses with separate rotation and translation confidences over overlapping image windows, then aggregates these predictions via a confidence‑weighted module to produce a single trajectory. CalfVO achieves the highest accuracy among calibration‑free methods across five benchmarks and runs at 53 FPS, outperforming all baselines.
By Vladimir Yugay, Duy-Kien Nguyen, Theo Gevers, Cees G. M. Snoek, Martin R. Oswald
RYOPO is an end‑to‑end query‑based RGB‑D set predictor that jointly detects, segments, and estimates 9‑DoF poses of unseen instances within known categories without relying on external instance segmentation or CAD priors. It uses shared image and scene encoding, a query‑conditioned geometry pathway, and object‑centric refinement with pose‑conditioned cross‑attention to achieve accurate pose estimation. On benchmark datasets such as NOCS, REAL275, and HouseCat6D, RYOPO outperforms published methods and runs in real time at 31.8 FPS on an RTX A6000.
By Hakjin Lee, Junghoon Seo, Jaehoon Sim
arXiv:2610.23039v1 Announce Type: new
Abstract: Feed-forward Gaussian models have made novel view synthesis almost instantaneous. Feed-forward methods predict Gaussians directly, either in two stages...
By Viruthshaan Vinasirajan, Ranga Rodrigo
The paper introduces EgoGenEval, a new benchmark that assesses the physical consistency of visual generators under ego‑motion by measuring Camera Motion Grounding and Scene State Preservation across 1,400 cases and 2,360 target views. Experiments on 16 pose‑free generators and two pose‑conditioned references show that current models struggle to maintain both camera motion and scene state simultaneously. A follow‑up study using EgoGen‑Train demonstrates that pairwise supervision does not effectively improve both metrics together, suggesting the need for a trajectory‑centric training paradigm.
By Yilin Long, Chenming Zhu, Zitang Gou, Jingli Lin, Tai Wang
GPA‑VGGT is a training‑free acceleration technique for the VGGT feed‑forward geometry model. It replaces VGGT’s global attention in early blocks with frame‑wise attention that uses a shared cross‑frame key/value set, and in later blocks it merges only keys and values while preserving queries and restoring attention mass. The method achieves speedups comparable to existing efficiency approaches while maintaining over 99% of VGGT’s pose accuracy on multi‑view geometry tasks.
By Muyeol Sung, Jangwon Kim, Jongwoo Lim
The paper introduces OVIE, a monocular novel-view synthesis method that eliminates the need for multi‑view training data. By using a frozen depth estimator to generate pseudo‑target views from single images and applying masked and adversarial losses, OVIE is trained on 30 million uncurated images. It achieves state‑of‑the‑art performance on RealEstate10K and DL3DV, produces highly consistent multi‑view trajectories, and runs at 116 FPS—over 600× faster than the fastest baseline.
By Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez, David Picard
arXiv:2610.09173v1 Announce Type: new
Abstract: 3D foundation models enable efficient novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction. Howev...
By Zhijie Zheng, Xinhao Xiang, Jiawei Zhang
The paper introduces EgoGenEval, a benchmark that assesses visual generators’ physical consistency during ego‑motion by measuring Camera Motion Grounding and Scene State Preservation across 1,400 cases and 2,360 target views. It shows that current pose‑free models struggle to maintain both camera motion and scene state, and that pairwise supervision in training does not simultaneously improve these aspects. The authors suggest a trajectory‑centric approach that couples self‑conditioned rollouts with explicit pose and visibility supervision to address these limitations.